2 papers
cs.AI2026
Bounded Morality: Defining the Space of Moral Computation
Max Kanwal, Caryn Tran, Patrick Mineault
Moral cognition has traditionally been modeled as adherence to fixed ethical theories--deontology, consequentialism, virtue ethics--implemented as static rules or value functions.…
cs.AI2026
Constructive Alignment: Governing Preference Dynamics in Human-AI Interaction
Max Kanwal, Caryn Tran
Most approaches to AI alignment treat human preferences as fixed targets to be inferred and optimized. This assumption conflicts with extensive empirical evidence showing that pref…